LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
Paper • 2603.03269 • Published • 61
Zachary Bessinger
zbessinger
·
AI & ML interests
Multimodal Computer Vision
Recent Activity
liked a model 9 days ago
Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF liked a dataset 9 days ago
nohurry/Opus-4.6-Reasoning-3000x-filtered liked a dataset 11 days ago
Idavidrein/gpqaOrganizations
None yet
upvoted 6
papers 16 days ago
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper • 2603.09906 • Published • 73
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
Paper • 2603.07660 • Published • 84
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 117
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing
Paper • 2603.03143 • Published • 144
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
Paper • 2603.12255 • Published • 90
upvoted a paper 5 months ago